INDEX

Explanations

references to academic-related metrics and awards

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

фе

-0.47

MotionEvent

-0.46

きょう

-0.44

MessageTagHelper

-0.43

IntoConstraints

-0.43

 Freeman

-0.43

ച്

-0.42

JNIEnv

-0.42

-0.41

терии

-0.41

POSITIVE LOGITS

TagMode

0.91

 >=",

0.90

kháu

0.77

IUrlHelper

0.76

 ویکی‌پدی

0.72

)");

0.71

 Theſe

0.71

ьаж

0.70

 utafitiHapana

0.69

 ویکی‌پدیای

0.69

Activations Density 0.125%

references to academic-related metrics and awards

No Comments

No Known Activations